Update app.py

app.py

@@ -1,64 +1,51 @@
+import pandas as pd
+import numpy as np
 import gradio as gr
+import faiss
+from sentence_transformers import SentenceTransformer
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+# --- Load data ---
+df = pd.read_csv("tariff_codes.csv")
+descriptions = df["description"].astype(str).tolist()
+codes = df["code"].astype(str).tolist()
+
+# --- Create embeddings ---
+embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
+embeddings = embedding_model.encode(descriptions, convert_to_numpy=True)
+
+# --- FAISS index (cosine similarity = inner product on normalized vectors) ---
+dim = embeddings.shape[1]
+faiss.normalize_L2(embeddings)
+index = faiss.IndexFlatIP(dim)
+index.add(embeddings)
+
+# --- Hugging Face Inference API client ---
+client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
+
+# --- RAG response generation ---
+def generate_answer(user_query):
+    query_embedding = embedding_model.encode([user_query], convert_to_numpy=True)
+    faiss.normalize_L2(query_embedding)
+    _, indices = index.search(query_embedding, k=5)
+
+    retrieved_context = "\n".join([f"{codes[i]}: {descriptions[i]}" for i in indices[0]])
+    prompt = f"""Here are some tariff code descriptions:
+{retrieved_context}
+
+Question: {user_query}
+Answer:"""
+
+    response = client.text_generation(
+        prompt,
+        max_new_tokens=200,
+        temperature=0.7,
+        stop_sequences=["\n\n"]
+    )
+    return response.strip()
+
+# --- Gradio Chat Interface ---
+gr.ChatInterface(
+    fn=generate_answer,
+    title="Tariff Code RAG Bot (FAISS + Inference API)"
+).launch()